Updated compression_config to quantization_config

config.json

@@ -8,7 +8,29 @@
   "attn_logit_softcapping": 50.0,
   "bos_token_id": 2,
   "cache_implementation": "hybrid",
-  "compression_config": {
+  "eos_token_id": 1,
+  "final_logit_softcapping": 30.0,
+  "head_dim": 256,
+  "hidden_act": "gelu_pytorch_tanh",
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 2304,
+  "initializer_range": 0.02,
+  "intermediate_size": 9216,
+  "max_position_embeddings": 8192,
+  "model_type": "gemma2",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 26,
+  "num_key_value_heads": 4,
+  "pad_token_id": 0,
+  "query_pre_attn_scalar": 256,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.0",
+  "use_cache": true,
+  "vocab_size": 256000,
+  "quantization_config": {
     "config_groups": {
       "group_0": {
         "input_activations": null,
@@ -37,27 +59,5 @@
     "kv_cache_scheme": null,
     "quant_method": "compressed-tensors",
     "quantization_status": "frozen"
-  },
-  "eos_token_id": 1,
-  "final_logit_softcapping": 30.0,
-  "head_dim": 256,
-  "hidden_act": "gelu_pytorch_tanh",
-  "hidden_activation": "gelu_pytorch_tanh",
-  "hidden_size": 2304,
-  "initializer_range": 0.02,
-  "intermediate_size": 9216,
-  "max_position_embeddings": 8192,
-  "model_type": "gemma2",
-  "num_attention_heads": 8,
-  "num_hidden_layers": 26,
-  "num_key_value_heads": 4,
-  "pad_token_id": 0,
-  "query_pre_attn_scalar": 256,
-  "rms_norm_eps": 1e-06,
-  "rope_theta": 10000.0,
-  "sliding_window": 4096,
-  "torch_dtype": "float32",
-  "transformers_version": "4.44.0",
-  "use_cache": true,
-  "vocab_size": 256000
+  }
 }